Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 608 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6936. Min Act: -0.0002

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5241. Min Act: -0.0001

Data Index: 494872 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.3119. Min Act: -0.0001

Data Index: 1357257 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.1502. Min Act: -0.0001

Data Index: 1248529 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.0753. Min Act: -0.0001

Data Index: 822274 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.8566. Min Act: -0.0001

Data Index: 342487 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.4795. Min Act: -0.0001

Data Index: 529653 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.6064. Min Act: -0.0002

Data Index: 881996 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.5453. Min Act: -0.0001

Data Index: 894380 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.6066. Min Act: -0.0001

Data Index: 252642 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.4485. Min Act: -0.0001

Data Index: 833326 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.4303. Min Act: -0.0001

Data Index: 14146 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.5560. Min Act: -0.0001

Data Index: 1125461 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.4177. Min Act: -0.0002

Data Index: 1158955 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.3827. Min Act: -0.0002

Data Index: 401859 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.3850. Min Act: -0.0002

Data Index: 1284105 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.3860. Min Act: -0.0001

Data Index: 1228686 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.2570. Min Act: -0.0001

Data Index: 1053294 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.5851. Min Act: -0.0002

Data Index: 938708 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 3.6936. Min Range: -3.6936

Max Act: 2.2001. Min Act: -0.0001

Data Index: 285243 (C4 (Web Text))

Max Activating Token Index: 653